Understanding AI Agents
The purpose of this post is to develop an understanding of AI Agents. They are a major development in deep learning for 2024. Conceptually, they leverage feedback loops between LLMs directing output from one into input to the other.
The below snippet from DeepLearning.AI's short course on AI Agentic Design Patterns with AutoGen is a nice example that demonstrates the idea with two LLM instances named "cathy" and "joe" who are comedians piggybacking off of each other's punchlines.
Below is a nice concrete instance of the termination criteria alluded to in the first abstract diagram for this same example. Once one of the LLMs produces output that includes "I gotta go" or "Goodbye" then the feedback loop between the agents ends.
Microsoft's autogen library is being used to create the AI Agents and in this example, the popular Open AI ChatGPT 3.5 serves as the model.
References:
Practical Multi AI Agents and Advanced Use Cases with crewAI - DeepLearning.AI
AI Agentic Design Patterns with AutoGen - DeepLearning.AI
AI Agents in LangGraph - DeepLearning.AI
Serverless Agentic Workflows with Amazon Bedrock - DeepLearning.AI
Comments
Post a Comment